Method and apparatus for generating a surrounding image

Abstract

The present invention relates to a method and to an apparatus for generating a surrounding image. The method for generating a surrounding image according to the present invention comprises the steps of: taking, as an input, images captured by cameras installed in the front and the rear of a vehicle and in the left and right sides of the vehicle, via respective channels connected to the cameras; correcting the captured images into a top view form to generate a plurality of corrected images; performing an overlaying process on the plurality of corrected images using a mask image containing region information on each channel and weight information for pixels constituting each region to generate a surrounding image of the vehicle; and displaying the thus-generated surrounding image. The present invention removes blind spots around the vehicle, and corrects the overlapped images captured by a plurality of cameras into natural images, thus enabling drivers to accurately recognize the surrounding situation of the vehicle. Therefore, a driver may park a vehicle in a convenient manner, and drive the vehicle in a forward or a backward direction in a safe manner even without looking at a side-view mirror or a rearview mirror.

What is claimed is: 
     
       1. A method for generating a vehicle surrounding image comprising:
 receiving images captured by cameras installed to front, rear, left, and right sides of a vehicle via channels connected to the cameras respectively; 
 generating a plurality of corrected images by correcting the captured images in a top view form; 
 generating a surrounding image of the vehicle by overlay-processing the plurality of the corrected images using a mask image containing region information per channel and weight information for pixels constituting at least one region; and 
 displaying the surrounding image; 
 wherein the plurality of the corrected images is generated using a look-up table, 
 wherein overlapping regions between the plurality of the corrected images are overlay-processed using the following equation:
     I ′( t+ 1)=α I   1 ( t )+(1−α) I   2 ( t ), 0≦α≦1
 
 
 
       where I 1 (t) and I 2 (t) denote image information for the overlapping region input via two channels respectively, α denotes a weight for pixels in the overlapping region, and I′(t+1) denotes the overlay-processed image information,
 wherein the mask image is set to attain a Gradient weight for the pixels in the overlapping region; and 
 wherein the mask image includes a first region duplicately captured through the front camera and the left camera of a vehicle, a third region duplicately captured through the front camera and the right camera of the vehicle, a seventh region duplicately captured through the rear camera and the left camera of the vehicle, a ninth region duplicately captured through the rear camera and the right camera of the vehicle, a second region captured through the front camera of the vehicle, without being duplicately captured through any other camera, a fourth region captured through the left camera of the vehicle, without being duplicately captured through any other camera, a sixth region captured through the right camera of the vehicle, without being duplicately captured through any other camera, an eighth region captured through the rear camera of the vehicle, without being duplicately captured through any other camera, and a fifth region on which an image corresponding to the vehicle is displayed; and 
 wherein the generating the surrounding image includes controlling the mask image to display the second, fourth, sixth, and eighth regions in monochrome without color change, to adjust R, G, and B pixel values of the fifth region, and to set an R pixel value of each pixel in the first, third, seventh, and ninth regions to a Gradient weight value between 1 and 254 for color matching. 
 
     
     
       2. The method of  claim 1 , wherein the generating of the plurality of the corrected images comprises:
 correcting distortion of the captured images according to lens distortion of the cameras; 
 transforming a viewpoint of the captured images into the top view form; and 
 rotating, translating, or scaling the captured images transformed into the top view form. 
 
     
     
       3. The method of  claim 1 , wherein the generating of the plurality of the corrected images comprises:
 correcting distortion of the captured images according to lens distortion of the cameras; 
 and projective transforming the captured images into a rectangular top view form. 
 
     
     
       4. The method of  claim 1 , further comprising:
 calculating an average brightness value of four indicators through the camera installed to the front side and applying the average brightness value to the surrounding image. 
 
     
     
       5. An apparatus for generating a vehicle surrounding image comprising:
 an image input part for receiving images captured by cameras installed to front, rear, left, and right sides of a vehicle via channels connected to the cameras respectively; 
 an image processing part for generating a plurality of corrected images by correcting the captured images into a top view form; 
 an image synthesis part for generating a surrounding image of the vehicle by overlay-processing the plurality of the corrected images using a mask image containing region information per channel and weight information for pixels constituting at least one region; 
 a display part for displaying the surrounding image; and 
 a control part for overlay-processing overlapping regions between the plurality of the corrected images,
 wherein the overlapping regions between the plurality of the corrected images are overlay-processed using the following equation:
     I ′( t+ 1)=α I   1 ( t )+(1−α) I   2 ( t ), 0≦α≦1
 
 
 
 
       where I 1 (t) and I 2 (t) denote image information for the overlapping region input via two channels respectively, α denotes a weight for pixels in the overlapping region, and I′(t+1) denotes the overlay-processed image information,
 wherein the mask image is set to attain a Gradient weight for the pixels in the overlapping region, 
 wherein the plurality of the corrected images is generated using a look-up table, and 
 wherein the mask image includes a first region duplicately captured through the front camera and the left camera of a vehicle, a third region duplicately captured through the front camera and the right camera of the vehicle, a seventh region duplicately captured through the rear camera and the left camera of the vehicle, a ninth region duplicately captured through the rear camera and the right camera of the vehicle, a second region captured through the front camera of the vehicle, without being duplicately captured through any other camera, a fourth region captured through the left camera of the vehicle, without being duplicately captured through any other camera, a sixth region captured through the right camera of the vehicle, without being duplicately captured through any other camera, an eighth region captured through the 
 
       rear camera of the vehicle, without being duplicately captured through any other camera, and a fifth region on which an image corresponding to the vehicle is displayed;
 wherein the generating the surrounding image includes controlling the mask image to display the second, fourth, sixth, and eighth regions in monochrome without color change, to adjust R, G, and B pixel values of the fifth region, and to set an R pixel value of each pixel in the first, third, seventh, and ninth regions to a Gradient weight value between 1 and 254 for color matching. 
 
     
     
       6. The apparatus of  claim 5 , wherein the image processing part corrects distortion of the captured images according to lens distortion of the cameras, transforms a viewpoint of the captured images into the top view form, and rotates, translates, or scales the captured images transformed into the top view form. 
     
     
       7. The apparatus of  claim 6 , further comprising:
 a communication part for receiving and providing driving state information of the vehicle to the control part, wherein the control part determines whether to display the surrounding image according to the driving state of the vehicle. 
 
     
     
       8. A system for generating a vehicle surrounding image comprising:
 a plurality of cameras installed to front, rear, left, and right sides of a vehicle for outputting captured images via respective channels; 
 an image generating apparatus for generating a plurality of corrected images by correcting the input captured images into a top view form, and generating a surrounding image of the vehicle by overlay-processing the plurality of the corrected images using a mask image containing region information per channel and weight information for pixels constituting at least one region; and 
 a display apparatus for displaying the surrounding image; 
 wherein the image generating apparatus overlay-processes overlapping regions between the plurality of the corrected images, 
 wherein the overlapping regions between the plurality of the corrected images are overlay-processed using the following equation:
     I ′( t+ 1)=α I   1 ( t )+(1−α) I   2 ( t ), 0≦α≦1
 
 
 
       where I 1 (t) and I 2 (t) denote image information for the overlapping region input via two channels respectively, α denotes a weight for pixels in the overlapping region, and I′(t+1) denotes the overlay-processed image information,
 wherein the mask image is set to attain a Gradient weight for the pixels in the overlapping region, 
 wherein the plurality of the corrected images is generated using a look-up table, and 
 wherein the mask image includes a first region duplicately captured through the front camera and the left camera of a vehicle, a third region duplicately captured through the front camera and the right camera of the vehicle, a seventh region duplicately captured through the rear camera and the left camera of the vehicle, a ninth region duplicately captured through the rear camera and the right camera of the vehicle, a second region captured through the front camera of the vehicle, without being duplicately captured through any other camera, a fourth region captured through the left camera of the vehicle, without being duplicately captured through any other camera, a sixth region captured through the right camera of the vehicle, without being duplicately captured through any other camera, an eighth region captured through the rear camera of the vehicle, without being duplicately captured through any other camera, and a fifth region on which an image corresponding to the vehicle is displayed; and 
 wherein the generating the surrounding image includes controlling the mask image to display the second, fourth, sixth, and eighth regions in monochrome without color change, to adjust R, G, and B pixel values of the fifth region, and to set an R pixel value of each pixel in the first, third, seventh, and ninth regions to a Gradient weight value between 1 and 254 for color matching.